How to Use the EBI PDBe MCP in LangChain

Q: Can my LangChain chain handle multiple structural lookups using the EBI PDBe MCP server?

Yes. You can build a ReAct agent that uses searchstructures to find PDB IDs, then loops through getsummary and getqualityscores for each result. LangSmith traces the inputs and outputs of each tool call in real time.

Fetch 3D macromolecular data directly into your LangChain pipelines to build precise, multi-step structural biology chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EBI PDBe MCP to LangChain

Create your Vinkius account to connect EBI PDBe to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup EBI PDBe with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Structural Queries in LangChain

`get_summary` initiates the sequence by pulling basic resolution and experimental data for any PDB ID. Your LangChain agent evaluates this output to decide whether to call `get_quality_scores` or halt the chain if the resolution is too low for your modeling criteria. Every step of this decision tree registers in LangSmith, giving you full observability over token costs and tool execution times. You see exactly how the agent parses the structural metadata before moving to downstream analysis.

Chain Residue and Ligand Mapping

`get_uniprot_mapping` links sequence-level UniProt accessions directly to 3D spatial coordinates in the PDB file. Your chain feeds this mapping into `get_binding_sites` to pinpoint exactly where ligands interact with specific residues. This sequential execution lets your agent build a detailed structural profile without manual intervention. By passing data from one tool to the next, you eliminate manual lookup errors in your bioinformatics pipelines.

Automate Complex Assembly Checks

`get_assemblies` retrieves the quaternary state of a protein to determine if it functions as a monomer or dimer. The output feeds directly into `get_ligand_monomers` to verify if bound small molecules sit at a protein interface. You configure this logic inside a LangGraph state machine, allowing the agent to loop through multiple assemblies until it matches your target criteria. This MCP Server setup replaces brittle, hard-coded scripts with flexible, data-driven pathways.

Setup guide

Set up EBI PDBe MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes EBI PDBe tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ebi-pdbe-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent EBI PDBe transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by PDBe (Protein Data Bank in Europe). All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect EBI PDBe now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about EBI PDBe MCP in LangChain

Install langchain-mcp-adapters and langgraph. Initialize the server connection using MultiServerMCPClient with the Vinkius endpoint, then pass the tools from client.get_tools() to your agent constructor.

Yes. You can build a ReAct agent that uses search_structures to find PDB IDs, then loops through get_summary and get_quality_scores for each result. LangSmith traces the inputs and outputs of each tool call in real time.

You handle rate limiting at the adapter or client level by configuring backoff strategies. The server executes queries sequentially within your chain, preventing sudden bursts that trigger API limits on the EBI servers.

Yes, you can run this server alongside vector database tools or chemical property APIs. Your agent can pull structural data using get_ligand_monomers and immediately query a local database to fetch matching SMILES strings.

Your search terms and PDB IDs go directly to the EBI PDBe API through a secure V8 sandbox on Vinkius. No structural coordinates or query parameters are stored or used to train external models.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript